{"id":"W2282238149","doi":"10.3138/jvme.0115-008r","title":"Using the <i>Nudge</i> and <i>Shove</i> Methods to Adjust Item Difficulty Values","year":2015,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Quality (philosophy); Psychology; Simple (philosophy); Computer science; Cognitive psychology; Applied psychology; Mathematics education","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02266995,0.0001176822,0.0003384451,0.0002962898,0.0001301579,0.0001594857,0.0007740572,0.00009078986,0.00007862973],"category_scores_gemma":[0.2450514,0.00006037121,0.00008976578,0.001210513,0.0001258481,0.0002813076,0.0002256669,0.0003298106,0.000004573949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007212612,"about_ca_system_score_gemma":0.0007914283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002064254,"about_ca_topic_score_gemma":4.725009e-7,"domain_scores_codex":[0.9951989,0.001728675,0.0009193864,0.0002153151,0.001744244,0.0001934534],"domain_scores_gemma":[0.9802113,0.0167636,0.0007963877,0.0003884959,0.0009627324,0.0008775525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001368177,0.0001732223,0.00518327,0.000007131173,0.00001853273,0.00001820282,0.001957537,0.00004555037,0.002865496,0.00007587384,0.06958883,0.9199296],"study_design_scores_gemma":[0.00186209,0.003946256,0.1273686,0.0004165368,0.0001464984,0.0168972,0.04073865,0.008822026,0.0006044694,0.03328139,0.765328,0.0005882895],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.8820703,0.002237142,0.09884565,0.01144773,0.004527527,0.00009512786,8.03188e-7,0.000008679834,0.0007670345],"genre_scores_gemma":[0.4337981,0.0001181395,0.5580748,0.006309983,0.001451879,0.000003975278,4.421458e-7,0.0000137015,0.0002290309],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9193413,"threshold_uncertainty_score":0.7856999,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7883825166976349,"score_gpt":0.6299458838527838,"score_spread":0.1584366328448511,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}